Public/koboldcpp
1
0
Fork 0
mirror of https://github.com/LostRuins/koboldcpp.git synced 2026-09-19 09:15:18 +02:00
Code Issues Packages Projects Releases Wiki Activity

Merge commit '533b18257b7da879a5de39f5d6437041e0e42c39' into concedo_experimental

Browse Source 
# Conflicts:
#	CMakeLists.txt
#	examples/gguf-hash/CMakeLists.txt
#	examples/gguf-hash/gguf-hash.cpp
#	scripts/sync_vendor.py
#	tools/mtmd/CMakeLists.txt
#	vendor/hash/rotate-bits/rotate-bits.h
#	vendor/hash/sha1/sha1.c
#	vendor/hash/sha1/sha1.h
#	vendor/hash/sha256/sha256.c
#	vendor/hash/sha256/sha256.h
#	vendor/hash/xxhash/xxhash.c
#	vendor/hash/xxhash/xxhash.h
This commit is contained in:
Concedo
2026-08-20 18:42:18 +08:00
parent f0cd0225aa 533b18257b
commit fc84597f96
28 changed files with 8000 additions and 40 deletions
Download Patch File Download Diff File Expand all files Collapse all files
src/llama-vocab.cpp
+17 -4
View File
@@ -2664,17 +2664,24 @@ void llama_vocab::impl::load(llama_model_loader & ml, const LLM_KV & kv) {
const uint32_t n_tokens = gguf_get_arr_n(ctx, token_idx);
const float * scores = nullptr;
const int * iscores = nullptr;
const int score_idx = gguf_find_key(ctx, kv(LLM_KV_TOKENIZER_SCORES).c_str());
if (score_idx != -1) {
if (gguf_get_kv_type(ctx, score_idx) != GGUF_TYPE_ARRAY ||
gguf_get_arr_type(ctx, score_idx) != GGUF_TYPE_FLOAT32) {
const gguf_type kv_type = gguf_get_kv_type(ctx, score_idx);
const gguf_type arr_type = kv_type == GGUF_TYPE_ARRAY ? gguf_get_arr_type(ctx, score_idx) : GGUF_TYPE_COUNT;
if (arr_type != GGUF_TYPE_INT32 &&
arr_type != GGUF_TYPE_FLOAT32) {
throw std::runtime_error(format("invalid gguf type for %s", kv(LLM_KV_TOKENIZER_SCORES).c_str()));
}
const uint32_t n_scores = gguf_get_arr_n(ctx, score_idx);
if (n_scores < n_tokens) {
throw std::runtime_error("Index out of array bounds for scores (" + std::to_string(n_scores) + " < " + std::to_string(n_tokens) + ")\n");
}
scores = (const float * ) gguf_get_arr_data(ctx, score_idx);
if (arr_type == GGUF_TYPE_INT32) {
iscores = (const int *) gguf_get_arr_data(ctx, score_idx);
} else {
scores = (const float * ) gguf_get_arr_data(ctx, score_idx);
}
}
const int * toktypes = nullptr;
@@ -2708,7 +2715,13 @@ void llama_vocab::impl::load(llama_model_loader & ml, const LLM_KV & kv) {
auto & token_data = id_to_token[i];
token_data.text = std::move(word);
token_data.score = scores ? scores[i] : 0.0f;
if (scores) {
token_data.score = scores[i];
} else if (iscores) {
token_data.score = static_cast<float>(iscores[i]);
} else {
token_data.score = 0.0f;
}
token_data.attr = LLAMA_TOKEN_ATTR_NORMAL;
if (toktypes) { //TODO: remove, required until per token attributes are available from GGUF file